Tool Wear State Identification Based on SVM Optimized by the Improved Northern Goshawk Optimization

• Published in: Sensors
• Main Authors: Jiaqi Wang, Zhong Xiang, Xiao Cheng, Ji Zhou, Wenqi Li
• Format: Article in Journal/Newspaper
• Language: English
• Published: MDPI AG 2023
• Subjects: tool wear state identification; recursive feature elimination; improved northern goshawk optimization; support vector machine; Chemical technology; TP1-1185; Northern Goshawk
• Online Access: https://doi.org/10.3390/s23208591; https://doaj.org/article/038b4e8c163e43e1a12a824a49281c29

Tool wear condition significantly influences equipment downtime and machining precision, necessitating the exploration of a more accurate tool wear state identification technique. In this paper, the wavelet packet thresholding denoising method is used to process the acquired multi-source signals and extract several signal features. The set of features most relevant to the tool wear state is screened out by the support vector machine recursive feature elimination (SVM-RFE). Utilizing these selected features, we propose a tool wear state identification model, which utilizes an improved northern goshawk optimization (INGO) algorithm to optimize the support vector machine (SVM), hereby referred to as INGO-SVM. The simulation tests reveal that INGO demonstrates superior convergence efficacy and stability. Furthermore, a milling wear experiment confirms that this approach outperforms five other methods in terms of recognition accuracy, achieving a remarkable accuracy rate of 97.9%.